Add files

.gitignore

@@ -0,0 +1,162 @@
+gradio_cached_examples/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

.pre-commit-config.yaml

@@ -0,0 +1,60 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-executables-have-shebangs
+      - id: check-json
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-toml
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+      - id: requirements-txt-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/myint/docformatter
+    rev: v1.7.5
+    hooks:
+      - id: docformatter
+        args: ["--in-place"]
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        args: ["--profile", "black"]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.11.2
+    hooks:
+      - id: mypy
+        args: ["--ignore-missing-imports"]
+        additional_dependencies:
+          [
+            "types-python-slugify",
+            "types-requests",
+            "types-PyYAML",
+            "types-pytz",
+          ]
+  - repo: https://github.com/psf/black
+    rev: 24.8.0
+    hooks:
+      - id: black
+        language_version: python3.10
+        args: ["--line-length", "119"]
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.7.1
+    hooks:
+      - id: nbstripout
+        args:
+          [
+            "--extra-keys",
+            "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
+          ]
+  - repo: https://github.com/nbQA-dev/nbQA
+    rev: 1.8.7
+    hooks:
+      - id: nbqa-black
+      - id: nbqa-pyupgrade
+        args: ["--py37-plus"]
+      - id: nbqa-isort
+        args: ["--float-to-top"]

.python-version

@@ -0,0 +1 @@
+3.10

.vscode/settings.json

@@ -0,0 +1,30 @@
+{
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": false,
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.organizeImports": "explicit"
+        }
+    },
+    "[jupyter]": {
+        "files.insertFinalNewline": false
+    },
+    "black-formatter.args": [
+        "--line-length=119"
+    ],
+    "isort.args": ["--profile", "black"],
+    "flake8.args": [
+        "--max-line-length=119"
+    ],
+    "ruff.lint.args": [
+        "--line-length=119"
+    ],
+    "notebook.output.scrolling": true,
+    "notebook.formatOnCellExecution": true,
+    "notebook.formatOnSave.enabled": true,
+        "notebook.codeActionsOnSave": {
+            "source.organizeImports": "explicit"
+        }
+}

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 hysts
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,12 +1,12 @@
 ---
-title: MMMU Dataset Viewer
-emoji: 👁
-colorFrom: blue
-colorTo: gray
+title: MMMU dataset viewer
+emoji: ⚡
+colorFrom: red
+colorTo: purple
 sdk: gradio
 sdk_version: 4.44.1
 app_file: app.py
-pinned: false
+license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,169 @@
+#!/usr/bin/env python
+
+import ast
+import os
+
+import datasets
+import gradio as gr
+import PIL.Image
+
+DESCRIPTION = """\
+# [MMMU](https://huggingface.co/datasets/MMMU/MMMU) dataset viewer
+"""
+
+SHOW_ANSWER = os.getenv("SHOW_ANSWER", "false").lower() == "true"
+SHOW_QUESTION_DETAILS = os.getenv("SHOW_QUESTION_DETAILS", "false").lower() == "true"
+
+SUBJECTS = [
+    "Accounting",
+    "Agriculture",
+    "Architecture_and_Engineering",
+    "Art",
+    "Art_Theory",
+    "Basic_Medical_Science",
+    "Biology",
+    "Chemistry",
+    "Clinical_Medicine",
+    "Computer_Science",
+    "Design",
+    "Diagnostics_and_Laboratory_Medicine",
+    "Economics",
+    "Electronics",
+    "Energy_and_Power",
+    "Finance",
+    "Geography",
+    "History",
+    "Literature",
+    "Manage",
+    "Marketing",
+    "Materials",
+    "Math",
+    "Mechanical_Engineering",
+    "Music",
+    "Pharmacy",
+    "Physics",
+    "Psychology",
+    "Public_Health",
+    "Sociology",
+]
+ds = {subject: datasets.load_dataset("MMMU/MMMU", name=subject, split="validation") for subject in SUBJECTS}
+
+
+def set_default_subject() -> str:
+    return "Accounting"
+
+
+def get_images(subject: str, question_index: int) -> list[PIL.Image.Image]:
+    images = []
+    for image_id in range(1, 8):
+        image = ds[subject][question_index][f"image_{image_id}"]
+        if image is None:
+            break
+        images.append(image)
+    return images
+
+
+def update_subject(
+    subject: str,
+) -> tuple[
+    gr.Textbox,  # Number of Questions
+    gr.Slider,  # Question Index
+    gr.Gallery,  # Images
+    gr.Textbox,  # Question
+    gr.Textbox,  # Options
+    gr.Textbox,  # Answer
+    gr.Textbox,  # Explanation
+    gr.Textbox,  # Topic Difficulty
+    gr.Textbox,  # Question Type
+    gr.Textbox,  # Subfield
+]:
+    return (
+        gr.Textbox(value=len(ds[subject])),  # Number of Questions
+        gr.Slider(label="Question Index", minimum=0, maximum=len(ds[subject]) - 1, step=1, value=0),  # Question Index
+    ) + update_question(subject, 0)
+
+
+def update_question(subject: str, question_index: int) -> tuple[
+    gr.Gallery,  # Images
+    gr.Textbox,  # Question
+    gr.Textbox,  # Options
+    gr.Textbox,  # Answer
+    gr.Textbox,  # Explanation
+    gr.Textbox,  # Topic Difficulty
+    gr.Textbox,  # Question Type
+    gr.Textbox,  # Subfield
+]:
+    question = ds[subject][question_index]
+
+    options = ast.literal_eval(question["options"])
+    options_str = "\n".join([f"{chr(65 + i)}. {option}" for i, option in enumerate(options)])
+    images = get_images(subject, question_index)
+    return (
+        gr.Gallery(value=images, columns=min(len(images), 2)),  # Images
+        gr.Textbox(value=question["question"]),  # Question
+        gr.Textbox(value=options_str),  # Options
+        gr.Textbox(value=question["answer"]),  # Answer
+        gr.Textbox(value=question["explanation"]),  # Explanation
+        gr.Textbox(value=question["topic_difficulty"]),  # Topic Difficulty
+        gr.Textbox(value=question["question_type"]),  # Question Type
+        gr.Textbox(value=question["subfield"]),  # Subfield
+    )
+
+
+with gr.Blocks(css="style.css") as demo:
+    gr.Markdown(DESCRIPTION)
+    with gr.Row():
+        subject = gr.Dropdown(label="Subject", choices=SUBJECTS)
+        question_count = gr.Textbox(label="Number of Questions")
+
+    with gr.Group():
+        question_index = gr.Slider(label="Question Index")
+        with gr.Row():
+            with gr.Column():
+                question = gr.Textbox(label="Question")
+                options = gr.Textbox(label="Options")
+            with gr.Column():
+                images = gr.Gallery(label="Images", object_fit="scale-down")
+
+    with gr.Accordion("Answer and Explanation", open=SHOW_ANSWER):
+        with gr.Row():
+            answer = gr.Textbox(label="Answer")
+            explanation = gr.Textbox(label="Explanation")
+
+    with gr.Accordion("Question Details", open=SHOW_QUESTION_DETAILS):
+        with gr.Row():
+            topic_difficulty = gr.Textbox(label="Topic Difficulty")
+            question_type = gr.Textbox(label="Question Type")
+            subfield = gr.Textbox(label="Subfield")
+
+    subject.change(
+        fn=update_subject,
+        inputs=subject,
+        outputs=[
+            question_count,
+            question_index,
+            images,
+            question,
+            options,
+            answer,
+            explanation,
+            topic_difficulty,
+            question_type,
+            subfield,
+        ],
+        queue=False,
+        api_name=False,
+    )
+
+    question_index.input(
+        fn=update_question,
+        inputs=[subject, question_index],
+        outputs=[images, question, options, answer, explanation, topic_difficulty, question_type, subfield],
+        queue=False,
+        api_name=False,
+    )
+
+    demo.load(fn=set_default_subject, outputs=subject, queue=False, api_name=False)
+
+if __name__ == "__main__":
+    demo.queue(api_open=False).launch(show_api=False)

pyproject.toml

@@ -0,0 +1,11 @@
+[project]
+name = "mmmu-dataset-viewer"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "datasets>=3.0.1",
+    "gradio>=4.44.1",
+    "hf-transfer>=0.1.8",
+]

requirements.txt

@@ -0,0 +1,221 @@
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+aiofiles==23.2.1
+    # via gradio
+aiohappyeyeballs==2.4.3
+    # via aiohttp
+aiohttp==3.10.8
+    # via
+    #   datasets
+    #   fsspec
+aiosignal==1.3.1
+    # via aiohttp
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.6.0
+    # via
+    #   gradio
+    #   httpx
+    #   starlette
+async-timeout==4.0.3
+    # via aiohttp
+attrs==24.2.0
+    # via aiohttp
+certifi==2024.8.30
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.3.2
+    # via requests
+click==8.1.7
+    # via
+    #   typer
+    #   uvicorn
+contourpy==1.3.0
+    # via matplotlib
+cycler==0.12.1
+    # via matplotlib
+datasets==3.0.1
+    # via mmmu-dataset-viewer (pyproject.toml)
+dill==0.3.8
+    # via
+    #   datasets
+    #   multiprocess
+exceptiongroup==1.2.2
+    # via anyio
+fastapi==0.115.0
+    # via gradio
+ffmpy==0.4.0
+    # via gradio
+filelock==3.16.1
+    # via
+    #   datasets
+    #   huggingface-hub
+fonttools==4.54.1
+    # via matplotlib
+frozenlist==1.4.1
+    # via
+    #   aiohttp
+    #   aiosignal
+fsspec==2024.6.1
+    # via
+    #   datasets
+    #   gradio-client
+    #   huggingface-hub
+gradio==4.44.1
+    # via mmmu-dataset-viewer (pyproject.toml)
+gradio-client==1.3.0
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+hf-transfer==0.1.8
+    # via mmmu-dataset-viewer (pyproject.toml)
+httpcore==1.0.6
+    # via httpx
+httpx==0.27.2
+    # via
+    #   gradio
+    #   gradio-client
+huggingface-hub==0.25.1
+    # via
+    #   datasets
+    #   gradio
+    #   gradio-client
+idna==3.10
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+    #   yarl
+importlib-resources==6.4.5
+    # via gradio
+jinja2==3.1.4
+    # via gradio
+kiwisolver==1.4.7
+    # via matplotlib
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via
+    #   gradio
+    #   jinja2
+matplotlib==3.9.2
+    # via gradio
+mdurl==0.1.2
+    # via markdown-it-py
+multidict==6.1.0
+    # via
+    #   aiohttp
+    #   yarl
+multiprocess==0.70.16
+    # via datasets
+numpy==2.1.1
+    # via
+    #   contourpy
+    #   datasets
+    #   gradio
+    #   matplotlib
+    #   pandas
+    #   pyarrow
+orjson==3.10.7
+    # via gradio
+packaging==24.1
+    # via
+    #   datasets
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   matplotlib
+pandas==2.2.3
+    # via
+    #   datasets
+    #   gradio
+pillow==10.4.0
+    # via
+    #   gradio
+    #   matplotlib
+pyarrow==17.0.0
+    # via datasets
+pydantic==2.9.2
+    # via
+    #   fastapi
+    #   gradio
+pydantic-core==2.23.4
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.18.0
+    # via rich
+pyparsing==3.1.4
+    # via matplotlib
+python-dateutil==2.9.0.post0
+    # via
+    #   matplotlib
+    #   pandas
+python-multipart==0.0.12
+    # via gradio
+pytz==2024.2
+    # via pandas
+pyyaml==6.0.2
+    # via
+    #   datasets
+    #   gradio
+    #   huggingface-hub
+requests==2.32.3
+    # via
+    #   datasets
+    #   huggingface-hub
+rich==13.9.1
+    # via typer
+ruff==0.6.8
+    # via gradio
+semantic-version==2.10.0
+    # via gradio
+shellingham==1.5.4
+    # via typer
+six==1.16.0
+    # via python-dateutil
+sniffio==1.3.1
+    # via
+    #   anyio
+    #   httpx
+starlette==0.38.6
+    # via fastapi
+tomlkit==0.12.0
+    # via gradio
+tqdm==4.66.5
+    # via
+    #   datasets
+    #   huggingface-hub
+typer==0.12.5
+    # via gradio
+typing-extensions==4.12.2
+    # via
+    #   anyio
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   multidict
+    #   pydantic
+    #   pydantic-core
+    #   rich
+    #   typer
+    #   uvicorn
+tzdata==2024.2
+    # via pandas
+urllib3==2.2.3
+    # via
+    #   gradio
+    #   requests
+uvicorn==0.31.0
+    # via gradio
+websockets==12.0
+    # via gradio-client
+xxhash==3.5.0
+    # via datasets
+yarl==1.13.1
+    # via aiohttp

style.css

@@ -0,0 +1,11 @@
+h1 {
+  text-align: center;
+  display: block;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: #fff;
+  background: #1565c0;
+  border-radius: 100vh;
+}